Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2790 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2843. Min Act: -0.0000

Data Index: 14737 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2863. Min Act: -0.0000

Data Index: 112854 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2334. Min Act: -0.0000

Data Index: 910397 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1366214 (Python Code)

Max Activating Token Index: 63

Text #4

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2019. Min Act: -0.0000

Data Index: 929631 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1090960 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1815. Min Act: -0.0000

Data Index: 14978 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1894. Min Act: -0.0000

Data Index: 118491 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1745. Min Act: -0.0000

Data Index: 770535 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1856. Min Act: -0.0000

Data Index: 134689 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1738. Min Act: -0.0000

Data Index: 254725 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1712. Min Act: -0.0000

Data Index: 548608 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1797. Min Act: -0.0000

Data Index: 417172 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1780. Min Act: -0.0000

Data Index: 336546 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1140689 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1370. Min Act: -0.0000

Data Index: 1236921 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1642. Min Act: -0.0000

Data Index: 417880 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1683. Min Act: -0.0000

Data Index: 907303 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1608. Min Act: -0.0000

Data Index: 191958 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1427964 (Python Code)

Max Activating Token Index: 943